© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8320
    Prev
    Next
    INDEX
    Explanations

    Reuters, Vim, ANS, exits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ifter
    -0.09
     foundations
    -0.08
    cola
    -0.08
    antee
    -0.08
     hm
    -0.08
    ToDevice
    -0.08
    sse
    -0.08
    berry
    -0.08
     ,-
    -0.08
    iset
    -0.08
    POSITIVE LOGITS
     alley
    0.10
     exiting
    0.10
    fal
    0.10
     Exiting
    0.09
    ãĤŃ
    0.09
     Understand
    0.09
     Alley
    0.09
    INAL
    0.09
    obot
    0.09
    amas
    0.09
    Activations Density 0.001%

    No Known Activations